{
  "category": "Qwen2.5 CUDA GQA ABI",
  "model": "Qwen/Qwen2.5-0.5B-Instruct",
  "revision": "7ae557604adf67be50417f59c2c2f167def9a775",
  "model_type": "qwen2",
  "command": "mobius build --model Qwen/Qwen2.5-0.5B-Instruct --revision 7ae557604adf67be50417f59c2c2f167def9a775 --dtype f16 --ep cuda --external-data onnx --runtime onnx-genai OUTPUT",
  "mobius_source_commit": "c977dae714f197398f8c28ac0efc27214c3b0431",
  "mobius_branch": "justinchuby/catalogue-small-builds",
  "external_data": true,
  "real_weights": true,
  "distribution_repo": "justinchuby/onnx-genai-example-qwen2-5-0-5b-cuda-gqa-f16",
  "distribution_url": "https://huggingface.co/justinchuby/onnx-genai-example-qwen2-5-0-5b-cuda-gqa-f16",
  "source_license": "apache-2.0",
  "source_url": "https://huggingface.co/Qwen/Qwen2.5-0.5B-Instruct/tree/7ae557604adf67be50417f59c2c2f167def9a775"
}